REVIEW 1 cited by
Learning to Reverse DNNs from AI Programs Automatically
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
With the privatization deployment of DNNs on edge devices, the security of on-device DNNs has raised significant concern. To quantify the model leakage risk of on-device DNNs automatically, we propose NNReverse, the first learning-based method which can reverse DNNs from AI programs without domain knowledge. NNReverse trains a representation model to represent the semantics of binary code for DNN layers. By searching the most similar function in our database, NNReverse infers the layer type of a given function's binary code. To represent assembly instructions semantics precisely, NNReverse proposes a more fine-grained embedding model to represent the textual and structural-semantic of assembly functions.
Forward citations
Cited by 1 Pith paper
-
LeMix: Unified Scheduling for LLM Training and Inference on Multi-GPU Systems
LeMix co-locates LLM serving and retraining on shared GPUs with profiler-driven scheduling, reporting up to 3.53x throughput gains over separated deployments.
Discussion (0). Continue with ORCID to comment.